Automatic Segmentation of the Self-organizing Map to Support Territorial Zoning

Abstract

This paper proposes an algorithm for analyzing clusters of thematic maps with ordinal categorical classes to support territorial zoning. The proposed method combines the Self-Organizing Map with graph segmentation techniques for data clustering. The approach was evaluated with synthetic data and applied to the environmental zoning of the Alto Taquari basin, MS/MT. The results showed the ability of the algorithm to separate the data into unimodal differentiable groups.